Research map / Vision-language and multimodal / Cross-modal learning
Online Asymmetric Similarity Learning for Cross-Modal Retrieval
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Extend CMOS with multiple kernels and combine their weights using hedging | CMOS cross-modal retrieval · Wiki | average MAP: 0.333 -> 0.411 | Helped |
| Extend CMOS with multiple kernels and combine their weights using hedging | CMOS cross-modal retrieval · Pascal VOC 2007 | average MAP: 0.593 -> 0.708 | Helped |
| Extend CMOS with multiple kernels and combine their weights using hedging | CMOS cross-modal retrieval · NUS-WIDE | average MAP: 0.553 -> 0.581 | Helped |
| Add text-to-image triplets to image-to-text triplet training (ablation) | CMOS · Pascal VOC 2007 | average MAP: 0.583 -> 0.593 | Helped |
| Add image-to-text triplets to text-to-image triplet training (ablation) | CMOS · Pascal VOC 2007 | average MAP: 0.59 -> 0.593 | Helped |
| Train with both directional triplet types rather than image-to-text triplets alone (ablation) | CMOS · Pascal VOC 2007 image-to-text retrieval | MAP: 0.579 -> 0.586 | Helped |
| Train with both directional triplet types rather than text-to-image triplets alone (ablation) | CMOS · Pascal VOC 2007 image-to-text retrieval | MAP: +0.009 | Helped |
| Train with both directional triplet types rather than image-to-text triplets alone (ablation) | CMOS · Pascal VOC 2007 text-to-image retrieval | MAP: +0.014 | Helped |
| Train with both directional triplet types rather than text-to-image triplets alone (ablation) | CMOS · Pascal VOC 2007 text-to-image retrieval | MAP: 0.603 -> 0.600 | No clear effect |
Closest papers by meaning
- Deep Supervised Cross-Modal Retrieval (CVPR 2019 · similarity 0.89)
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (AAAI 2025 · similarity 0.89)
- A Differentiable Semantic Metric Approximation in Probabilistic Embedding for Cross-Modal Retrieval (NeurIPS 2022 · similarity 0.89)
- Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval (CVPR 2024 · similarity 0.88)
- Robust Semi-paired Multimodal Learning for Cross-modal Retrieval (AAAI 2026 · similarity 0.88)
- Adaptive Prompt-Based Semantic Embedding with Inspire Potential of Implicit Knowledge for Cross-Modal Retrieval (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.